5 papers accepted for Interspeech 2026!

2026

1. YODAS v3: Over 1 Million Hours of High-Bandwidth, Stereophonic, Multilingual Speech

   William Chen ,  Shinnosuke Takamichi ,  Sayaka Shiota ,  Satoru Fukayama ,  Samuele Cornell ,  and  Shinji Watanabe

   In Proceedings of Interspeech , Sep 2026

   Bib

   @inproceedings{chen26interspeech_yodas-v3,
     abbr_publisher = {Proceedings of Interspeech},
     booktitle = {Proceedings of Interspeech},
     title = {YODAS v3: Over 1 Million Hours of High-Bandwidth, Stereophonic, Multilingual Speech},
     author = {Chen, William and Takamichi, Shinnosuke and Shiota, Sayaka and Fukayama, Satoru and Cornell, Samuele and Watanabe, Shinji},
     year = {2026},
     month = sep
   }

2. ELSA: Acoustic Event-Level Semantic Alignment for Fine-Grained Reference-Free Text-to-Audio Evaluation

   Shuntaro Suzuki ,  Kento Tokura ,  Daichi Yashima ,  Kanon Amemiya ,  Komei Sugiura ,  and  Shinnosuke Takamichi

   In Proceedings of Interspeech , Sep 2026

   Bib

   @inproceedings{suzuki26interspeech_elsa,
     abbr_publisher = {Proceedings of Interspeech},
     booktitle = {Proceedings of Interspeech},
     title = {ELSA: Acoustic Event-Level Semantic Alignment for Fine-Grained Reference-Free Text-to-Audio Evaluation},
     author = {Suzuki, Shuntaro and Tokura, Kento and Yashima, Daichi and Amemiya, Kanon and Sugiura, Komei and Takamichi, Shinnosuke},
     year = {2026},
     month = sep
   }

3. What Makes Us Hate Our Own Voice? Large-scale experiments on Playback–Imagery Gaps and Individual–Speech Feature Effects

   Koki Fukuda ,  and  Shinnosuke Takamichi

   In Proceedings of Interspeech , Sep 2026

   Bib

   @inproceedings{fukuda26interspeech_own-voice,
     abbr_publisher = {Proceedings of Interspeech},
     booktitle = {Proceedings of Interspeech},
     title = {What Makes Us Hate Our Own Voice? Large-scale experiments on Playback--Imagery Gaps and Individual--Speech Feature Effects},
     author = {Fukuda, Koki and Takamichi, Shinnosuke},
     year = {2026},
     month = sep
   }

4. On the Effect of Segmentation Width and Cluster Size on Speech Resynthesis and Continuation in Generative Spoken Language Models

   Shunsuke Kando ,  Wataru Nakata ,  Shinnosuke Takamichi ,  and  Yusuke Miyao

   In Proceedings of Interspeech , Sep 2026

   Bib

   @inproceedings{kando26interspeech_speech-resynthesis,
     abbr_publisher = {Proceedings of Interspeech},
     booktitle = {Proceedings of Interspeech},
     title = {On the Effect of Segmentation Width and Cluster Size on Speech Resynthesis and Continuation in Generative Spoken Language Models},
     author = {Kando, Shunsuke and Nakata, Wataru and Takamichi, Shinnosuke and Miyao, Yusuke},
     year = {2026},
     month = sep
   }

5. Do speech foundation models perceive speaker similarity as humans do?

   Minoru Kishi ,  Hayato Yagi ,  Shinnosuke Takamichi ,  and  Yuki Saito

   In Proceedings of Interspeech , Sep 2026

   Bib

   @inproceedings{kishi26interspeech_speaker-similarity,
     abbr_publisher = {Proceedings of Interspeech},
     booktitle = {Proceedings of Interspeech},
     title = {Do speech foundation models perceive speaker similarity as humans do?},
     author = {Kishi, Minoru and Yagi, Hayato and Takamichi, Shinnosuke and Saito, Yuki},
     year = {2026},
     month = sep
   }